GPU model · price + stock · hourly snapshot

Nvidia RTX 3090 cloud rental prices

Name: Nvidia RTX 3090 cloud GPU rental
Brand: Nvidia
Availability: InStock

7 providers list the Nvidia RTX 3090, 5 have it in stock. Prices run from $0.13 to $0.22 per GPU hour — the same card, 1.7x apart.

Ampere 24 GB VRAM Q3 2020 16 configurations

LIVE Prices and stock checked 1 minute ago November 4, 2026 UTC

Cheapest in stock

$0.13

Clore.ai

Median

$0.18

across 7 providers

Most expensive

$0.22

same card, 1.7x the price

You overpay by

27%

if you take the median instead of the floor

Providers

Every provider renting the Nvidia RTX 3090

All providers →

Billing:

On-demandfrom $0.13/hr5 providers in stockPay as you go, stop any time.Spotfrom $0.087/hr2 providers in stockCheaper, but the provider can take the machine back.Reservednone listedPrepay a term for the lowest hourly rate.

Providers renting the Nvidia RTX 3090, in stock first, then cheapest first
Provider	Country	Configs	Scale	From	Stock	Days in stock	Grab
Clore.ai	—	2	1x-1x	$0.13	In stock	14/14	Grab
Vast.ai	United States of America	2	4x-4x	$0.15 per sec	In stock	60/60	Grab
OctaSpace	—	1	1x-1x	$0.18	In stock	14/14	Grab
Lium	—	1	1x-1x	$0.19	In stock	28/28	Grab
SimplePod	—	1	1x-1x	$0.20	In stock	11/14	Grab
Compshare	China	8	1x-8x	$0.18	Not reported	0/4	Grab
Runpod	United States of America	1	1x-1x	$0.22 per sec	Not reported	54/54	Grab

In stock first, then cheapest. Stock is what the provider reported at our last check. One GPU for a month (730h) at $0.13: $95. Lium publishes live counts: 104 GPUs at $0.19, 92% rented.

Price history

Price trend

Cheapest Nvidia RTX 3090 rate has risen 64.6% since Sep 6 — $0.068 → $0.11/GPU/hr.

$0.112 /GPU/hr · Nov 4

One point per day: the lowest listed $/GPU/hr across every provider we track, captured daily. 180 offers in the latest snapshot.

Configurations

All 16 configurations

In stock only16 of 16 configurations

Nvidia RTX 3090 configurations from every provider
Configuration	Provider	Region	VRAM	vCPU	RAM	Per GPU/hr	Total/hr	Stock
1x NVIDIA GeForce RTX 3090SpotClore.ai	Clore.ai	UA	24 GB	—	64 GB	$0.09	$0.09	In stock
4x RTX 3090SpotVast.ai	Vast.ai	CN	96 GB	96	126 GB	$0.11per sec	$0.43	In stock
1x NVIDIA GeForce RTX 3090Clore.ai	Clore.ai	UA	24 GB	—	64 GB	$0.13	$0.13	In stock
4x RTX 3090Vast.ai	Vast.ai	CN	96 GB	36	126 GB	$0.15per sec	$0.60	In stock
1x NVIDIA GeForce RTX 3090OctaSpace	OctaSpace	US	24 GB	36	62 GB	$0.18	$0.18	In stock
1x NVIDIA GeForce RTX 3090Lium	Lium	—	—	—	—	$0.19	$0.19	In stock
1x RTX 3090SimplePod	SimplePod	CA	24 GB	10	40 GB	$0.20	$0.20	In stock
1x RTX3090PreemptibleCompshare	Compshare	—	24 GB	16	64 GB	$0.12	$0.12	Not reported
8x RTX3090PreemptibleCompshare	Compshare	—	192 GB	124	512 GB	$0.12	$1.00	Not reported
2x RTX3090PreemptibleCompshare	Compshare	—	48 GB	32	128 GB	$0.12	$0.25	Not reported
4x RTX3090PreemptibleCompshare	Compshare	—	96 GB	64	256 GB	$0.12	$0.50	Not reported
1x RTX3090Compshare	Compshare	—	24 GB	16	64 GB	$0.18	$0.18	Not reported
2x RTX3090Compshare	Compshare	—	48 GB	32	128 GB	$0.18	$0.36	Not reported
8x RTX3090Compshare	Compshare	—	192 GB	124	512 GB	$0.18	$1.43	Not reported
4x RTX3090Compshare	Compshare	—	96 GB	64	256 GB	$0.18	$0.72	Not reported
1x RTX 3090Runpod	Runpod	—	24 GB	—	—	$0.22per sec	$0.22	Not reported

Model fit

What fits in 24 GB

The question behind most rentals: will the model load. Sized against one Nvidia RTX 3090.

VRAM required to serve open-weight LLMs on a Nvidia RTX 3090, by quantization precision
Model	16-bit	8-bit	4-bit
DeepSeek-V3 DeepSeek · 671B params · 37B active	1,610 GB 68× · 22 GB free	805 GB 34× · 11 GB free	403 GB 17× · 5 GB free
Llama 3.1 405B Meta · 405B params	972 GB 41× · 12 GB free	486 GB 21× · 18 GB free	243 GB 11× · 21 GB free
Qwen3 235B-A22B Alibaba · 235B params · 22B active	564 GB 24× · 12 GB free	282 GB 12× · 6 GB free	141 GB 6× · 3 GB free
Mixtral 8x22B Mistral · 141B params · 39B active	338 GB 15× · 22 GB free	169 GB 8× · 23 GB free	85 GB 4× · 11 GB free
Mistral Large 2 Mistral · 123B params	295 GB 13× · 17 GB free	148 GB 7× · 20 GB free	74 GB 4× · 22 GB free
gpt-oss-120b OpenAI · 117B params · 5.1B active	281 GB 12× · 7 GB free	140 GB 6× · 4 GB free	70 GB 3× · 2 GB free
Qwen2.5 72B Alibaba · 72.7B params	174 GB 8× · 18 GB free	87 GB 4× · 9 GB free	44 GB 2× · 4 GB free
Llama 3.3 70B Meta · 70.6B params	169 GB 8× · 23 GB free	85 GB 4× · 11 GB free	42 GB 2× · 6 GB free
Qwen3 32B Alibaba · 32.8B params	79 GB 4× · 17 GB free	39 GB 2× · 9 GB free	20 GB 1× · 4 GB free
Gemma 2 27B Google · 27.2B params	65 GB 3× · 7 GB free	33 GB 2× · 15 GB free	16 GB 1× · 8 GB free
Mistral Small 3 Mistral · 24B params	58 GB 3× · 14 GB free	29 GB 2× · 19 GB free	14 GB 1× · 10 GB free
Llama 3.1 8B Meta · 8B params	19 GB 1× · 5 GB free	10 GB 1× · 14 GB free	5 GB 1× · 19 GB free

Required memory is weights plus 20% for KV cache and runtime at short context; long contexts and large batches need more. Cells tinted green fit on a single Nvidia RTX 3090.

Specifications

Nvidia RTX 3090 specifications

Nvidia RTX 3090 hardware specifications
Architecture	Ampere
Memory per GPU	24 GB GDDR6X
Memory bandwidth	936 GB/s
Release date	Q3 2020
GPU interconnect	NVLink 112 GB/s
FP16 / BF16 compute rate	71.2 TFLOPS (dense), 142.4 with sparsity
INT8 compute rate	284.7 TOPS (dense), 569.4 with sparsity
Process node	Samsung 8N
Board power	350 W

Alternatives

Every provider renting the Nvidia RTX 3090

Price trend

All 16 configurations

What fits in 24 GB

Nvidia RTX 3090 specifications

Alternatives to the Nvidia RTX 3090